Sentiment analysis with generative AI: a data-driven PaLM 2 prompt evaluation

The new era of generative artificial intelligence (“GenAI”) – and specifically the advent of large language models (“LLMs”) – promises to rapidly broaden the population of developers who can implement sentiment analysis in their applications. But what guarantees do developers have that an LLM will answer correctly? How can developers take extra steps to prove to downstream users that their prompts are accurate? In this blog post, we provide a simple overview of how to evaluate the quality of a sentiment analysis prompt.